Sökning: onr:"swepub:oai:DiVA.org:kth-341954" > Diffusion-Based Tim...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03385naa a2200505 4500 | |
001 | oai:DiVA.org:kth-341954 | |
003 | SwePub | |
008 | 240108s2023 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3419542 URI |
024 | 7 | a https://doi.org/10.1145/3611643.36138662 DOI |
040 | a (SwePub)kth | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a kon2 swepub-publicationtype |
100 | 1 | a Yang, Fangkaiu Microsoft, China4 aut |
245 | 1 0 | a Diffusion-Based Time Series Data Imputation for Cloud Failure Prediction at Microsoft 365 |
264 | 1 | b Association for Computing Machinery (ACM),c 2023 |
338 | a print2 rdacarrier | |
500 | a Part of ISBN 9798400703270QC 20240108 | |
520 | a Ensuring reliability in large-scale cloud systems like Microsoft 365 is crucial. Cloud failures, such as disk and node failure, threaten service reliability, causing service interruptions and financial loss. Existing works focus on failure prediction and proactively taking action before failures happen. However, they suffer from poor data quality, like data missing in model training and prediction, which limits performance. In this paper, we focus on enhancing data quality through data imputation by the proposed Diffusion+, a sample-efficient diffusion model, to impute the missing data efficiently conditioned on the observed data. Experiments with industrial datasets and application practice show that our model contributes to improving the performance of downstream failure prediction. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Programvaruteknik0 (SwePub)102052 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Software Engineering0 (SwePub)102052 hsv//eng |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Annan data- och informationsvetenskap0 (SwePub)102992 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Other Computer and Information Science0 (SwePub)102992 hsv//eng |
653 | a Diffusion model | |
653 | a disk failure prediction | |
653 | a missing data imputation | |
700 | 1 | a Yin, Wenjieu KTH,Robotik, perception och lärande, RPL4 aut0 (Swepub:kth)u1it1cm1 |
700 | 1 | a Wang, Luu Microsoft, China4 aut |
700 | 1 | a Li, Tianciu Microsoft, China4 aut |
700 | 1 | a Zhao, Puu Microsoft, China4 aut |
700 | 1 | a Liu, Bou Microsoft, China4 aut |
700 | 1 | a Wang, Paulu Microsoft, China4 aut |
700 | 1 | a Qiao, Bou Microsoft, China4 aut |
700 | 1 | a Liu, Yudongu Microsoft, China4 aut |
700 | 1 | a Björkman, Mårten,d 1970-u KTH,Robotik, perception och lärande, RPL4 aut0 (Swepub:kth)u1cs4x4i |
700 | 1 | a Rajmohan, Saravanu Microsoft, USA4 aut |
700 | 1 | a Lin, Qingweiu Microsoft, China4 aut |
700 | 1 | a Zhang, Dongmeiu Microsoft, China4 aut |
710 | 2 | a Microsoft, Chinab Robotik, perception och lärande, RPL4 org |
773 | 0 | t ESEC/FSE 2023 - Proceedings of the 31st ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineeringd : Association for Computing Machinery (ACM)g , s. 2050-2055q <2050-2055 |
856 | 4 | u https://doi.org/10.1145/3611643.3613866y Fulltext |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-341954 |
856 | 4 8 | u https://doi.org/10.1145/3611643.3613866 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy